Multi-hierarchy feature extraction and multi-step cost aggregation for stereo matching

Article Computer Science, Artificial Intelligence

Context-sensitive zero-shot semantic segmentation model based on meta-learning

Wenjian Wang et al.

Summary: This paper proposes a novel zero-shot semantic segmentation model based on meta-learning, which effectively solves the problem of bias towards known categories in complex scenarios by adjusting the parameters of the dual-space, and outperforms existing best methods in zero-shot segmentation tasks.

NEUROCOMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Global context-aware multi-scale features aggregative network for salient object detection

Inam Ullah et al.

Summary: This paper introduces a deep convolutional neural network model for salient object detection, utilizing modules like multi-scale feature extraction and cross feature aggregation to achieve more accurate results.

NEUROCOMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Light-weight network for real-time adaptive stereo depth estimation

Wanshui Gan et al.

Summary: The lightweight adaptive network (LWANet) proposed in this paper combines self-supervised learning methods to achieve online adaptive stereo depth estimation with low computation cost and GPU memory space. By utilizing pseudo 3D convolution and CSPN network, the network strikes a better balance between accuracy and computational cost, effectively addressing the domain shift problem for embedded devices like NVIDIA Jetson TX2.

NEUROCOMPUTING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

FC-DCNN: A densely connected neural network for stereo estimation

Dominik Hirner et al.

Summary: This paper introduces a novel lightweight network for stereo estimation, which computes matching costs and performs post-processing using FC-DCNN. By avoiding traditional cost-aggregation methods, the network shows good performance in various benchmarks.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

Add to Collection

Article Computer Science, Artificial Intelligence